Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2606 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9642. Min Act: -0.1700

Data Index: 4174071 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9653. Min Act: -0.1700

Data Index: 5764814 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9595. Min Act: -0.1699

Data Index: 3070245 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9512. Min Act: -0.1700

Data Index: 7273887 (Open Web Text)

Max Activating Token Index: 185

Text #4

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9474. Min Act: -0.1700

Data Index: 3735632 (Open Web Text)

Max Activating Token Index: 80

Text #5

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9468. Min Act: -0.1700

Data Index: 351064 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9300. Min Act: -0.1700

Data Index: 5217309 (Open Web Text)

Max Activating Token Index: 119

Text #7

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9352. Min Act: -0.1700

Data Index: 3187736 (Open Web Text)

Max Activating Token Index: 442

Text #8

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9279. Min Act: -0.1700

Data Index: 1487525 (Open Web Text)

Max Activating Token Index: 214

Text #9

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9304. Min Act: -0.1699

Data Index: 8458712 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9021. Min Act: -0.1700

Data Index: 2334946 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9153. Min Act: -0.1700

Data Index: 8593024 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9031. Min Act: -0.1700

Data Index: 4340254 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8999. Min Act: -0.1700

Data Index: 1431846 (Open Web Text)

Max Activating Token Index: 303

Text #14

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8950. Min Act: -0.1700

Data Index: 3317142 (Open Web Text)

Max Activating Token Index: 423

Text #15

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9027. Min Act: -0.1700

Data Index: 7308967 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.9101. Min Act: -0.1700

Data Index: 4846782 (Open Web Text)

Max Activating Token Index: 128

Text #17

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8915. Min Act: -0.1697

Data Index: 1173069 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8874. Min Act: -0.1700

Data Index: 4586857 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 1.9653. Min Range: -1.9653

Max Act: 1.8908. Min Act: -0.1700

Data Index: 6909759 (Open Web Text)

Max Activating Token Index: 237